Tech

Subspace Node Pruning

By Joshua Offergeld, John Chidiac, Marcel van Gerven, Nasir Ahm · arXiv cs.LG

cs.CVcs.LGcs.NE

arXiv:2405.17506v4 Announce Type: replace Abstract: Node pruning is the art of removing computational units such as neurons, filters, attention heads, or even entire layers to significantly reduce inference time while retaining…

Published: November 4, 2026 (17 h ago)
Outlet: arXiv cs.LG
Section: Tech
Length here: Headline and 31-word snippet. The full article is at the source.

More from arXiv cs.LG and around the same time

A semiconductor wafer being lifted from processing equipment

Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBencharXiv:2611.03727v1 Announce Type: new Abstract: Benchmarks built from model hubs combine interaction data, knowledge graphs (KGs) and resource documentation, but valid files do not ensure that these artifacts describe the same…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

CaRe-KT: Continuity-Aware Retrieval-Augmented Reasoning for Knowledge TracingarXiv:2611.03744v1 Announce Type: new Abstract: Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning. Retrieval-augmented KT improves these estimates using…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

Community detection in complex networks via node similarity, graph representation learning, and hierarchical clusteringarXiv:2303.12212v3 Announce Type: replace-cross Abstract: Community detection is a significant challenge in analysing real graphs, including social, citation, biological, and many other networks. This article proposes three new…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

Correlations Are Ruining Your Gradient DescentarXiv:2407.10780v5 Announce Type: replace Abstract: Natural gradient descent, and the preconditioned optimizers which have followed from it, correct gradient descent by estimating curvature and applying its inverse to the…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error AnalysisarXiv:2503.01036v3 Announce Type: replace-cross Abstract: We introduce a novel kernel-based framework for learning differential equations and their solution maps. The framework is efficient in its data requirements in terms of…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated LearningarXiv:2611.03724v1 Announce Type: new Abstract: In receiver-directed federated learning, each site draws a trust boundary. For every source and model component it judges, on its own data, whether the transfer helps (admit), harms…arXiv cs.LG · 17 h ago · reads at arXiv cs.LG

This page holds the headline and a short snippet as published by arXiv cs.LG, whose feed they came from. The story itself, the photography and the rights stay with them, and the button above goes straight to their site. We keep this page so the headline has a stable address and a record of when it ran.